How it works
Rarus Health turns patient messages, documents and check-ins into care signals. AI structures routine signals. A Care Manager reviews what needs judgment. Clinicians make medical decisions.
Rarus Health AI agent
Illustration. Not a real patient.
Each care signal shows what happened, what may need to happen next, what blocked it and who needs to know.
A message, voice note, document or check-in answer arrives on WhatsApp.
The AI reads it and pulls out what happened.
The priority tells the Care Manager how soon to look.
The Care Manager sees a summary and a suggested next action.
The care team receives only what needs clinical attention.
Illustration. Not a real patient. Bar lengths show the idea, not measured volumes.
Rarus Health automates five routine parts of care management. A Care Manager stays in control of each.
The Rarus Health AI agent works on WhatsApp, in Spanish or Portuguese. It answers from verified content, asks structured follow-up questions and flags signals that need a person.
The result: automated WhatsApp interactions support routine communication, while Care Managers handle situations requiring human attention according to the agreed service protocol.
A Care Manager can take over any conversation at any moment.
The AI agent answers from articles that a person has checked. Each answer links to its source.
The result: Care Managers stop answering the same question many times a week.
A person verifies every article before the AI agent can use it.
The AI reads photos, PDFs and voice notes, turns them into text and files them in the patient's record.
The result: nobody types up paper reports.
When the system is unsure how to file a document, a Care Manager checks it.
The AI keeps a short narrative of each patient's situation for the Care Manager and the care team.
The result: every contact starts from the full picture, not a blank page.
The narrative is written for the Care Manager and the care team. Patients do not receive it.
The AI flags each signal, sets a priority and drafts a reply. A Care Manager reviews the draft and passes medical questions to the care team.
The result: changes surface when they happen, not at the next visit.
A Care Manager approves every drafted reply to a health signal.
Patients and families talk to Rarus Health on WhatsApp, the app they already use every day.
A patient app loses families at download, registration and login. On WhatsApp, the first message starts the service.
Text, voice notes, photos and PDFs all work. A person who prefers to speak does not have to type.
Rarus Health runs the service and the Care Managers' console. The clinic installs nothing.
Rarus Health automates tasks, not decisions.
Rarus Health does not deliver care, diagnose or prescribe. The care team makes clinical decisions.
Automation changes the economics of care management. The same Care Managers can follow many more patients, and each patient receives more attention, not less.
More of the budget goes to the moments that need a person.
Continuity for a whole population, not only a priority group.
The care team hears about a change when it happens.
Each contact becomes a structured event. Partners receive aggregated, anonymized insight.
Rarus Health builds on the best available models and owns everything around them, so it can switch to a better model when one appears.
Rarus Health built its own system for care conversations on WhatsApp.
Program authors write questionnaires as content, with branching, scoring and consent steps built in.
The playbooks hold coordination guidance for each rare disease that Rarus Health covers.
Articles on rights, funding routes and patient organizations, country by country.
The record holds structured events of what happens between visits. No hospital system holds this record.
The suites test the AI against realistic conversations before each release.
A separate page explains how Rarus Health builds each of the five automated parts. It covers the architecture, the safety measures and the technology stack. Technology leaders and investors who run technical due diligence usually start there.
Ask for a demonstration of the service on WhatsApp, or for a technical briefing.
Identify where patients drop outDo you want to know who builds the technology? Meet the team.
